Model reference · open weights
Hy3 is an open-weight language model from tencent, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
[](#license) [](https://huggingface.co/tencent/Hy3-preview) [](https://modelscope.cn/models/Tencent-Hunyuan/Hy3-preview) [](https://cnb.cool/ai-models/tencent/Hy3-preview) [](https://ai.gitcode.com/tencenthunyuan/Hy3-preview) 🖥️ <a href="https://aistudio.tencent.com/"<bOfficial Website</b</a | 💬 <a href="https://github.com/Tencent-Hunyuan/Hy3-preview"<bGitHub</b</a</p Table of Contents - Model Introduction - Highlights - Benchmark Results - STEM & Reasoning - Context Learning & Instruction Following - Code & Agent - News - Model Links - Quickstart - Deployment - vLLM - SGLang - Training - Quantization - License - Contact Us Model Introduction Hy3 preview is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Hy3 preview is the first model trained on our rebuilt infrastructure, and the strongest we've shipped so far. It improves significantly on complex reasoning, instruction following, context learning, coding, and agent tasks. Highlights - STEM & Reasoning — Complex reasoning underpins everything else. Hy3 preview performs well on challenging STEM benchmarks like FrontierScience-Olympiad and IMOAnswerBench, and achieved excellent results in the Tsinghua Qiuzhen College Math PhD qualifying exam (Spring '26) and the China High School Biology Olympiad (CHSBO 2025), demonstrating generalizable reasoning capacity. - Context Learning & Instruction Following — Real-world tasks require the ability to parse messy, lengthy contexts and follow complex rules. We built CL-bench and CL-bench-Life from our own business scenarios to innovatively measure context learning ability. Hy3 preview exhibits solid gains in both context learning and instruction following capabilities. - Code & Agent — Coding and agents saw the biggest gains. With a rebuilt RL infrastructure and larger-scale training tasks, we posted competitive scores across mainstream coding agent benchmarks (SWE-bench Verified, Terminal-Bench 2.0) and search agent benchmarks (BrowseComp, WideSearch). Benchmark Results Pre-trained Model Performance
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | tencent |
|---|---|
| Type | Language models |
| Parameters (lead) | 298.8B |
| Variants | 2 |
| Runs with | transformers |
| Released | 2026-04-13 |
| Popularity | 60k downloads / month |
| Likes | 956 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys hy3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (hy3 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"hy3","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗